High Identification Rate Research Articles

Research on Anti-Frequency Sweeping Jamming Method for Frequency Modulation Continuous Wave Radio Fuze Based on Wavelet Packet Transform Features

Frequency modulation continuous wave (FMCW) radio fuze is widely used in military equipment, due to its excellent range and anti-jamming ability. However, the widespread use of radio fuze jammers on modern battlefields poses a serious threat to fuzes. In this study, a classification method of targeting and sweeping frequency jamming signals of FMCW radio fuze based on wavelet packet transform features is proposed, which improves the anti-jamming ability of fuze. The wavelet packet transform of the output signal of the radio fuze detector is used to form a feature vector, which is fed into a support vector machine for targeting and jamming signal classification. The experimental results of the measured data show that the proposed method can achieve a high accuracy rate of classification and identification of FMCW radio fuze targets and frequency sweeping jamming signals. The highest recognition accuracy reached is 98.81% ± 0.0037. The lowest false alarm probability is 0.57% ± 0.0043, which indicates its potential application values in the near future.

Intelligent Wear Debris Identification of Gearbox Based on Virtual Ferrographic Images and Two-Level Transfer Learning

Ferrography analysis is one of main means to identify wear state of mechanical equipment, and its key is the intelligent recognition of wear debris ferrographic images. Ferrographic image acquisition is a complex and time-consuming work, so the direct deep learning cannot been carried out for the small tested samples. A virtual ferrographic image dataset is prepared firstly and then two-level transfer learning scheme is proposed to improve the identification rate of the tested samples based on the deep learning model trained by the virtual samples. A combined network of YOLOv3 and DarkNet53 is constructed, and the application effect of model is improved by two-level transfer learning of virtual dataset to open dataset and then open dataset to tested dataset, and the model errors before and after twice transfer learning are analyzed. The average identification accuracy of the model in the validation dataset is 86.1%, which is 44.5% higher than that without two-level transfer learning, and the average recall reaches 95.8%. The experimental results prove the proposed method have a high identification rate for the tested ferrographic images of an actual gearbox.

DNA barcode reference library for the West Sahara-Sahel reptiles

DNA barcode reference libraries are now continuously produced for the tree of life, which are essential pillars for the study of biological diversity. Yet, our knowledge about global diversity is largely limited in undersampled regions such as the largest warm desert, the Sahara-Sahel. This dataset provides a DNA barcode reference library for the reptiles of the Western Sahara-Sahel (WSS) and neighbouring countries across this region. It includes 760 barcodes from 133 reptile taxa, distributed in 23 families, and covering the intraspecific diversity of some species. A total of 84 species were collected in the WSS (83% of the total reptile species richness) over 18 overland field expeditions conducted since 2003. DNA barcodes resulted in a high success rate (95%) of species identification and barcoding gap analysis highlighted the effectiveness of the COI fragment as a barcode marker for the WSS reptiles. This dataset represents a comprehensive and reliable DNA reference library for the WSS, filling an important biodiversity gap across a remote and hard-to-sample region.

Wayside Acoustic Fault Diagnosis of Train Bearing Based on Improved Linear Discriminant Analysis

Train bearing is one of the key parts of a train wheel, and its fault diagnosis is crucial for train safety. This paper proposes an Improved Linear Discriminant Analysis (ILDA) algorithm to diagnose train bearing faults. A new distance function is employed to adjust the between-class divergence matrix of LDA. The adjusted between-class divergence matrix is adopted for selecting the projection direction with the best clustering performance and reducing the ambiguity or overlap among different classes. The sample clustering evaluation index( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SI</i> ) is adopted to evaluate the clustering performance of fusion features obtained by ILDA. First, twenty-four original features are extracted from wayside acoustic signals after reducing the Doppler effect. Then, ILDA is adopted to extract fusion features. Finally, the train bearing faults are identified by extreme learning machine(ELM). The experimental results show that the fusion features extracted by the proposed method can be effectively identified, which have good clustering performance and high identification rate. Furthermore, the identification results of two datasets provided by different universities show that the fusion features obtained by ILDA also have good clustering performance and high identification rate, which further verify the validity of the proposed method.

A Novel Deep Learning and Ensemble Learning Mechanism for Delta-Type COVID-19 Detection.

Recently, the novel coronavirus disease 2019 (COVID-19) has posed many challenges to the research community by presenting grievous severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) that results in a huge number of mortalities and high morbidities worldwide. Furthermore, the symptoms-based variations in virus type add new challenges for the research and practitioners to combat. COVID-19-infected patients comprise trenchant radiographic visual features, including dry cough, fever, dyspnea, fatigue, etc. Chest X-ray is considered a simple and non-invasive clinical adjutant that performs a key role in the identification of these ocular responses related to COVID-19 infection. Nevertheless, the defined availability of proficient radiologists to understand the X-ray images and the elusive aspects of disease radiographic replies to remnant the biggest bottlenecks in manual diagnosis. To address these issues, the proposed research study presents a hybrid deep learning model for the accurate diagnosing of Delta-type COVID-19 infection using X-ray images. This hybrid model comprises visual geometry group 16 (VGG16) and a support vector machine (SVM), where the VGG16 is accustomed to the identification process, while the SVM is used for the severity-based analysis of the infected people. An overall accuracy rate of 97.37% is recorded for the assumed model. Other performance metrics such as the area under the curve (AUC), precision, F-score, misclassification rate, and confusion matrix are used for validation and analysis purposes. Finally, the applicability of the presumed model is assimilated with other relevant techniques. The high identification rates shine the applicability of the formulated hybrid model in the targeted research domain.

People’s Knowledge and Perceptions Towards Bee–Pollinators in the Southern Highlands, Tanzania: Conservation Implications and Strategies

Background and research aims Bees are important pollinators of flowering wild plants and agricultural crops that contribute significantly towards food security, improving people’s livelihoods, and maintaining genetic diversity in plant communities. However, the decline of the bee population due to anthropogenic changes and limited knowledge of bees is threatening bee diversity, particularly in sub–Saharan Africa. Negative perceptions, that is, fear and disgust, are common emotions that lead to a lack of support for bee conservation. Understanding local people’s perceptions is vital as it can help in bee conservation decision making and proper protection actions. Methods We conducted the study in the Mbeya and Songwe regions of Tanzania to assess the knowledge and perception of local people about bee–pollinators and conservation using a structured questionnaire Results We found that the majority of respondents (91%) have heard about bees (χ2 = 6275, p &lt; 0.001) and their conservation initiatives (71%), and about 84% of respondents consider bees to be important (χ2 = 168.9, p = 0.001). Moreover, Apis mellifera had the highest identification rate, with 52.7% of respondents. A binary logistic model revealed that respondents' knowledge of bee–pollinators and pollination is not influenced by their age (except for respondents aged 15–18 years, p = 0.012) and education level. While 74% of respondents claimed to be afraid of bees, 79% stated that bees are dangerous to humans. The most common cause is personal experience with bee stings. Poor farm management practices, for example, use of fire and deforestation, were noted by 79% of respondents as the most human activities threatening bee–pollinators. Conclusion Overall, the respondents were more familiar with A. mellifera compared to non–Apis bee species. Implications for conservation Thus, we suggest that implementation of pollinator management programs is vital to ensure their survival and reduce the perceived threat by dispelling myths and encouraging interest in bees.

Enhanced procedures for mosquito identification by MALDI-TOF MS

BackgroundIn the last decade, an innovative approach has emerged for arthropod identification based on matrix-assisted laser desorption ionization time-of-flight mass spectrometry (MALDI-TOF MS). Increasing interest in applying the original technique for arthropod identification has led to the development of a variety of procedures for sample preparation and selection of body parts, among others. However, the absence of a consensual strategy hampers direct inter-study comparisons. Moreover, these different procedures are confusing to new users. Establishing optimized procedures and standardized protocols for mosquito identification by MALDI-TOF MS is therefore a necessity, and would notably enable the sharing of reference MS databases. Here, we assess the optimal conditions for mosquito identification using MALDI-TOF MS profiling.MethodsThree homogenization methods, two of which were manual and one automatic, were used on three distinct body parts (legs, thorax, head) of two mosquito laboratory strains, Anopheles coluzzii and Aedes aegypti, and the results evaluated. The reproducibility of MS profiles, identification rate with relevant scores and the suitability of procedures for high-throughput analyses were the main criteria for establishing optimized guidelines. Additionally, the consequences of blood-feeding and geographical origin were evaluated using both laboratory strains and field-collected mosquitoes.ResultsRelevant score values for mosquito identification were obtained for all the three body parts assayed using MALDI-TOF MS profiling; however, the thorax and legs were the most suitable specimens, independently of homogenization method or species. Although the manual homogenization methods were associated with a high rate of identification on the three body parts, this homogenization mode is not adaptable to the processing of a large number of samples. Therefore, the automatic homogenization procedure was selected as the reference homogenization method. Blood-feeding status did not hamper the identification of mosquito species, despite the presence of MS peaks from original blood in the MS profiles of the three body parts tested from both species. Finally, a significant improvement in identification scores was obtained for field-collected specimens when MS spectra of species from the same geographical area were added to the database.ConclusionThe results of the current study establish guidelines for the selection of mosquito anatomic parts and modality of sample preparation (e.g. homogenization) for future specimen identification by MALDI-TOF MS profiling. These standardized operational protocols could be used as references for creating an international MS database.

Sentinel lymph node biopsy in high-risk cutaneous squamous cell carcinoma of the head and neck: Systematic review and meta-analysis.

The aim of our study was to better define the role of sentinel lymph node biopsy (SLNB) in high-risk cutaneous squamous cell carcinoma of the head and neck (cSCCHN). A systematic review and meta-analysis was performed according to the PRISMA statement. Seven-hundred and five patients were included from 20 studies. The pooled SLN identification rate was 98.8% (95%CI: 97.0-99.8). The median number of SLN excised was 3.6 (n=371, 95%CI: 2.0-4.4). The pooled SLNB positive rate and cumulative regional recurrence rate (RRR) in negative SLNB were 5.6% (95%CI: 2.6-9.6) and 2.9% (95%CI: 0.5-7.2), respectively. The high SLN identification rate demonstrates SLNB feasibility in cSCCHN. The low SLNB positive rate and the relatively high RRR raise some doubts concerning its clinical utility. Further studies are mandatory to define predictors of lymph node metastases able to better select patients that may benefit from a SLNB.

A Driver Identification Method for a Car Through a Wireless Communication

To prevent car thefts, we propose a driver identification method through a wireless communication using a smart phone and a system equipped with an NFC chip in a car. Driver identifications are carried out by approaching the driver’s NFC device to the NFC system in the car which does not require complicated systems to install the NFC in a car. For a theft case in which driver’s NFC code does not match to the registered, subsequent steps could be taken into action. In the proposed method, we can trace the stolen car by sending GPS information to the owner. The proposed method which does not require advanced technology to implement has high identification rates.

Estadificación ganglionar tras terapia sistémica primaria en mujeres con cáncer de mama y afectación ganglionar al diagnóstico

ObjectiveThe main objective of this study is to analyze the efficacy of combined axillary marking (lymph node clipping and sentinel lymph node biopsy (SLNB)) for axillary staging in patients with primary systemic treatment (PST) and pathologically confirmed node-positive breast cancer at diagnosis. The secondary objective is to determine the impact of lymph node marking in the suppression of axillary lymph node dissection (ALND) in the study group. MethodsWe conducted a prospective study in which lymph node staging was performed using wire localization of positive lymph nodes and a SLNB with dual tracer. All patients who presented no metastatic involvement of the sentinel lymph node (SLN) or clip/wire-marked lymph node were spared an ALND. The multidisciplinary committee agreed on axillary treatment for patients with lymph node involvement. ResultsEighty one patients met the inclusion criteria. We identified and extirpated the clip/wire-marked node in 80 of 81 patients (98.8%), with SLNB performed successfully in 88,9% of patients. The SLN and wire-marked node matched in 78.9% of patients; 76.2% of patients did not undergo ALND. ConclusionsThe combined axillary marking (clip and SLNB) in patients with metastatic lymph node at diagnosis and PST offers a high identification rate (98.8%%) and a high correlation between the wire-marked lymph node and the SLN (78.9%%). This procedure has enabled the suppression of ALND in 76.2% of patients.

Lymph node staging after primary systemic therapy in women with breast cancer and lymph node involvement at diagnosis

ObjectiveThe main objective of this study is to analyze the efficacy of combined axillary marking (lymph node clipping and sentinel lymph node biopsy (SLNB)) for axillary staging in patients with primary systemic treatment (PST) and pathologically confirmed node-positive breast cancer at diagnosis. The secondary objective is to determine the impact of lymph node marking in the suppression of axillary lymph node dissection (ALND) in the study group. MethodsWe conducted a prospective study in which lymph node staging was performed using wire localization of positive lymph nodes and a SLNB with dual tracer. All patients who presented no metastatic involvement of the sentinel lymph node (SLN) or clip/wire-marked lymph node were spared an ALND. The multidisciplinary committee agreed on axillary treatment for patients with lymph node involvement. Results: Eighty one patients met the inclusion criteria. We identified and extirpated the clip/ wire-marked node in 80 of 81 patients (98.8%), with SLNB performed successfully in 88,9% of patients. The SLN and wire-marked node matched in 78.9% of patients; 76.2% of patients did not undergo ALND. ConclusionsThe combined axillary marking (clip and SLNB) in patients with metastatic lymph node at diagnosis and PST offers a high identification rate (98.8%) and a high correlation between the wire-marked lymph node and the SLN (78.9%). This procedure has enabled the suppression of ALND in 76.2% of patients.

Document forgery detection using source printer identification: A comparative study of text‐dependent versus text‐independent analysis

AbstractSource printer identification represents an interesting modality for document forgery detection. Establishing the identity of the printer that was employed to print a questioned document allows concluding its authenticity. This paper investigates the effectiveness of deep visual features (learned using convolutional neural networks) in characterization of the source printer. Images of printed documents are divided into small patches as well as characters for extraction of features. An off‐the‐shelf recognition engine is also integrated, allowing experiments in text‐dependent as well as text‐independent modes. Experiments are carried out on a standard data set of documents from 20 different printers and identification rates of 95.52% and 98.06% are reported using patches and characters, respectively. Furthermore, the discriminating power of different characters, as well as their combinations, is also being studied. Unlike many existing techniques, which rely on pre‐segmented characters and report results by comparing same characters only, the proposed technique works on complete images of printed documents and reports high identification rates.

Intrusion identification using GMM-HMM for perimeter monitoring based on ultra-weak FBG arrays.

Intrusion identification has been an intractable task for perimeter security. One of the primary challenges is to possess high identification rate over a long-distance range monitoring. This paper proposes an intrusion identification scheme based on ultra-weak fiber Bragg grating (UWFBG) arrays. The scheme is acquired by the combination of a Gaussian mixture model (GMM) and a hidden Markov model (HMM). The time dependencies are obtained by the analysis of relevant sensors in UWFBG arrays from the procedure of intrusions. The features extracted from vibration signals with time dependencies are used as the input of GMM-HMM. The GMM-HMM simultaneously analyzes features and time dependencies to identify intrusion. Experimental demonstration verifies that the proposed scheme can identify three intrusions (walking, knocking and climbing) and two non-intrusions (heavy truck passing and wind blowing) with the average identification rate of 98.2%. By the comparison tests with other six classifiers, the proposed GMM-HMM scheme shows a solid performance in the integrated evaluation for intrusion identification.

New understanding of source profiles: Example of the coating industry

The source profiles of VOCs in the industry are closely related to the raw and auxiliary materials, process characteristics and waste gas treatment of the enterprise, as well as the number of VOCs that can be identified by analytical methods. In the process of industry transformation, it is necessary to update the source profiles. This study selects the coating industry as a case study as it is in a transitional stage and has high volatile organic compounds (VOCs) production and odor complaints. The VOCs emissions in seven coating enterprises in 2019 were studied using a broad-spectrum and high species identification rate analysis method to identify many new species of VOCs, which increased the total emissions by 6.4 times compared with previous studies. A total of 26 new types of VOCs pollutants were identified, especially the number of oxygenated VOCs species increased by 3.1 times, and proved that butyl acetate replaced the benzene series to become was the new dominant species in the coating industry. And the average ozone formation potential (OFP) of coating industry was 2.6 times the measurement result of the classic method of PAMs and TO15. The source reactivity increased on average by 366.7%.

Identification of Filamentous Fungi by MALDI-TOF Mass Spectrometry: Evaluation of Three Different Sample Preparation Methods and Validation of an In-House Species Cutoff.

Invasive infections caused by filamentous fungi constitute a leading cause of morbidity and mortality in immunocompromised patients. Rapid and reliable identification of filamentous fungi is essential for the early initiation of appropriate treatment. In the present study, 230 filamentous fungi isolates identified by conventional methods were investigated using MALDI-TOF MS (Bruker Daltonics, Bremen, Germany) in combination with the Filamentous Fungi Library 3.0 provided by the manufacturer. Three different sample preparation methods were applied as recommended by the manufacturer and identification rates were compared using the criteria provided by the manufacturer. Application of the more time-consuming sample preparation methods clearly improved identification at the species level. Thus, the identification rate increased from 48.9% using the simplest method to 76.1% with the most laborious procedure. Misidentifications did not occur. Furthermore, the reliability of an in-house threshold for species identification was investigated. The reduced threshold increased the rate of isolates correctly identified at the species level by up to 86.4%. As no misidentification was made at the genus level and only one misidentification of minor significance occurred at the species level, this threshold could be validated for routine use in our laboratory. In conclusion, regarding the high identification rates achieved, this commercial platform proved suitable for implementation in routine diagnosis.

Functional connectomes incorporating phase synchronization for the characterization and prediction of individual differences

BackgroundFunctional connectomes have been proven to be able to predict an individual’s traits, acting as a fingerprint. A majority of studies use the amplitude information of fMRI signals to construct the connectivity but it remains unknown whether phase synchronization can be incorporated for improved prediction of individual cognitive behaviors. MethodsIn this paper, we address the issue by extracting phase information from the fMRI time series with a phase locking approach, followed by the construction of functional connectomes. ResultsWe first examine the identification and prediction performance using phase-based profiles in comparison with amplitude-based connectomes. We then combine both phase-based and amplitude-based connectivity to extract subject-specific information enabled by the phase synchronization. Results show that high individual identification rates (from 82.7% to 92.6%) can be achieved by phase-based connectomes. Phase-based connectivity offers unique information complementary to amplitude-based signals. Intra-network phase-locking appears more informative for individual prediction. In addition, phase synchronization can be used to predict cognitive behaviors. Comparison with existing method: The amplitude-based connectivity cannot capture the subject-specific information due to neural synchronization. The comparison with other phase-based methods has been involved in the discussion session. ConclusionsOur findings suggest that neural synchronization carries subject-specific information, which can be captured by phase locking value. The incorporation of phase information into connectomes presents a promising approach to understand each individual brain’s uniqueness.

Guide Triangle Catalog Generation Based on Triangle Density and Utilization for Star Sensors

The guide star catalog is an important component of star identification algorithms for star sensors that indirectly determines their identification rate and other performance characteristics. Currently, star identification algorithms based on triangle features have high identification rates and strong anti-interference abilities. However, this type of method usually requires a large-size guide triangle catalog. Without proper construction, many triangles in the catalog are barely used in the pattern recognition process. In this paper, a guide triangle catalog generation method for star identification based on triangle density and utilization is proposed. First, a model of the star density and triangle density distribution in the celestial sphere is established. Then, considering factors such as the sizes and shapes of the triangles and the brightness levels of the stars, a triangle utilization model is established. Based on these models, a high-triangle-utilization, low-size guide triangle catalog is generated by eliminating low-utilization triangles to the greatest extent possible under the premise of ensuring a minimum triangle density. Some experiments were conducted to prove the performance of the proposed method. Compared with the existing methods under the same conditions, the size of the catalog constructed by the proposed method can be reduced by 70&#x0025;&#x2013;90&#x0025;. Because the selected triangles are different, the proposed catalog exhibits a higher identification rate than other catalogs of the same size.

Collaborative Care for Low-Income Patients From Racial-Ethnic Minority Groups in Primary Care: Engagement and Clinical Outcomes.

To assess model impact and opportunities for improvement, this study examined collaborative care model (CoCM) engagement and clinical outcomes among low-income patients from racial-ethnic minority groups with depression and anxiety. Starting in 2015, the CoCM was implemented in seven primary care practices of an urban academic medical center serving patients from racial-ethnic minority backgrounds, predominantly Medicaid beneficiaries. Eligible individuals scored positive for depressive or anxiety symptoms (or both) on the Patient Health Questionnaire-2 (PHQ-2) and PHQ-9 and the Generalized Anxiety Disorder Scale-2 (GAD-2) and GAD-7 during systematic screening in primary care settings. Screening rates and yield, patient characteristics, and CoCM engagement and outcomes were examined. Clinical improvement was measured by the difference in PHQ-9 and GAD-7 scores at baseline and at 10-to-14-week follow-up. High rates of screening (87%, N=88,236 of 101,091) and identification of individuals with depression or anxiety (13%, N=11,886) were observed, and 58% of 3,957 patients who engaged in minimally adequate CoCM treatment had significant clinical improvement. Nevertheless, only 56% of eligible patients engaged in the model, and 25% of those individuals did not return for at least one follow-up appointment. Being female with clinically significant comorbid anxiety and depressive symptoms and having Medicaid or commercial insurance increased the likelihood of CoCM engagement. CoCM can help engage vulnerable patients in behavioral health care and improve clinical symptoms. However, significant opportunity exists to advance the model's impact in treating depressive and anxiety disorders and decreasing health disparities by addressing engagement barriers.

Hybrid machine learning classification scheme for speaker identification.

Motivated by the requirement to prepare for the next generation of "Automatic Spokesperson Recognition" (ASR) system, this paper applied the fused spectral features with hybrid machine learning (ML) strategy to the speech communication field. This strategy involved the combined spectral features such as mel-frequency cepstral coefficients (MFCCs), spectral kurtosis, spectral skewness, normalized pitch frequency (NPF), and formants. The characterization of suggested classification method could possibly serve in advanced speaker identification scenarios. Special attention was given to hybrid ML scheme capable of finding unknown speakers equipped with speaker id-detecting classifier technique, known as "Random Forest-Support Vector Machine" (RF-SVM). The extracted speaker precise spectral attributes are applied to the hybrid RF-SVM classifier to identify/verify the particular speaker. This work aims to construct an ensemble decision tree on a bounded area with minimal misclassification error using a hybrid ensemble RF-SVM strategy. A series of standard, real-time speaker databases, and noise conditions are functionally tested to validate its performance with other state-of-the-art mechanisms. The proposed fusion method succeeds in the speaker identification task with a high identification rate (97% avg) and lower equal error rate (EER) (<2%), compared with the individual schemes for the recorded experimental dataset. The robustness of the classifier is validated using the standard ELSDSR, TIMIT, and NIST audio datasets. Experiments on ELSDSR, TIMIT, and NIST datasets show that the hybrid classifier produces 98%, 99%, and 94% accuracy, and EERs were 2%, 1%, and 2% respectively. The findings are then compared with well-known other speaker recognition schemes and found to be superior.

Magnetic Flux Transport Identification of Active Reconnection: MMS Observations in Earth’s Magnetosphere

Abstract Magnetic reconnection plays an important role in converting energy while modifying field topology. This process takes place under varied plasma conditions during which the transport of magnetic flux is intrinsic. Identifying active magnetic reconnection sites with in situ observations is challenging. A new technique, Magnetic Flux Transport (MFT) analysis, has been developed recently and proven in numerical simulation for identifying active reconnection efficiently and accurately. In this study, we examine the MFT process in 37 previously reported electron diffusion region (EDR)/reconnection-line crossing events at the day-side magnetopause and in the magnetotail and turbulent magnetosheath using Magnetospheric Multiscale measurements. The coexisting inward and outward MFT flows at an X-point provides a signature that magnetic field lines become disconnected and reconnected. The application of MFT analysis to in-situ observations demonstrates that MFT can successfully identify active reconnection sites under complex varied conditions, including asymmetric and turbulent upstream conditions. It also provides a higher rate of identification than plasma outflow jets alone. MFT can be applied to in situ measurements from both single- and multi-spacecraft missions and laboratory experiments.